Image de couverture de livre

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Zijun, Tu, Haoqin, Zhang, Letian, Chen, Hardy, Wu, Juncheng, Liu, Xiangyan, Yuan, Zhenlong, Pang, Tianyu, Shieh, Michael Qizhe, Liu, Fengze, Zheng, Zeyu, Yao, Huaxiu, Zhou, Yuyin, Xie, Cihang
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
par: Chen, Hardy, et autres
Publié: (2026)

ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
par: Wu, Juncheng, et autres
Publié: (2026)

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
par: Chen, Tianyu, et autres
Publié: (2026)

Kestrel: Grounding Self-Refinement for LVLM Hallucination Mitigation
par: Mao, Jiawei, et autres
Publié: (2026)

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
par: Xia, Peng, et autres
Publié: (2026)

QuantClaw: Precision Where It Matters for OpenClaw
par: Zhang, Manyi, et autres
Publié: (2026)

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
par: Liu, Songyang, et autres
Publié: (2026)

Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex
par: Yang, Zhonghao, et autres
Publié: (2026)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
par: Wu, Juncheng, et autres
Publié: (2026)

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
par: Yao, Hongwei, et autres
Publié: (2026)

Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
par: Shan, Zhengyang, et autres
Publié: (2026)

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
par: Qian, Zhaofang, et autres
Publié: (2025)

Security, Privacy, and Ethical Risks in OpenClaw
par: Jin, Yutong, et autres
Publié: (2026)

Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
par: Liu, Fazhong, et autres
Publié: (2026)

A Systematic Security Evaluation of OpenClaw and Its Variants
par: Wang, Yuhang, et autres
Publié: (2026)

Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains
par: Wu, Juncheng, et autres
Publié: (2025)

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
par: Chen, Hardy, et autres
Publié: (2025)

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
par: Zhang, Letian, et autres
Publié: (2026)

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
par: Liu, Yanqing, et autres
Publié: (2025)

ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation
par: Zhao, Haochen, et autres
Publié: (2026)

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
par: Li, Xianhang, et autres
Publié: (2025)

A Security Analysis of the OpenClaw AI Agent Framework
par: Suwansathit, Surada, et autres
Publié: (2026)

OpenClaw-RL: Train Any Agent Simply by Talking
par: Wang, Yinjie, et autres
Publié: (2026)

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
par: Liu, Xiangyan, et autres
Publié: (2025)

ViLBench: A Suite for Vision-Language Process Reward Modeling
par: Tu, Haoqin, et autres
Publié: (2025)

Foundations for Agentic AI Investigations from the Forensic Analysis of OpenClaw
par: Gruber, Jan, et autres
Publié: (2026)

Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents
par: Li, Zongwei, et autres
Publié: (2026)

Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
par: Wang, Zijun, et autres
Publié: (2026)

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
par: Ying, Zonghao, et autres
Publié: (2026)

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
par: Wu, Zijian, et autres
Publié: (2025)

OpenGo: An OpenClaw-Based Robotic Dog with Real-Time Skill Switching
par: Li, Hanbing, et autres
Publié: (2026)

A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?
par: Xie, Yunfei, et autres
Publié: (2024)

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
par: Deng, Xinhao, et autres
Publié: (2026)

Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills
par: Ding, Mingwei, et autres
Publié: (2026)

ROSClaw: An OpenClaw ROS 2 Framework for Agentic Robot Control and Interaction
par: Cardenas, Irvin Steve, et autres
Publié: (2026)

VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
par: Han, Qijun, et autres
Publié: (2026)

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
par: Batra, Hunar, et autres
Publié: (2025)

ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents
par: Lai, Yuxiang, et autres
Publié: (2026)

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
par: Wang, Zijun, et autres
Publié: (2025)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
par: Wang, Zijun, et autres
Publié: (2024)